© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-9B
    5. 20-RES-MATRYOSHKA-DC
    7. 135
    Prev
    Next
    INDEX
    Explanations

    occurrences of structured data or formatting indicators in text

    oai_token-act-pair · gpt-4o-mini
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     entregado
    -0.40
     Constitucional
    -0.40
     helft
    -0.39
     afbeelding
    -0.36
     orejas
    -0.36
     silvestre
    -0.35
     jste
    -0.35
     bezoek
    -0.34
    ymce
    -0.34
     galletas
    -0.34
    POSITIVE LOGITS
     ſche
    0.71
    Tikang
    0.63
    expandindo
    0.63
     pleaſure
    0.61
     myſelf
    0.61
    
    0.59
     ſtre
    0.57
     ujednoznacz
    0.57
    Diweddarwch
    0.57
     rodríguez
    0.57
    Activations Density 0.348%

    No Known Activations